INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    matic
    -0.08
    993
    -0.07
    )].
    -0.07
    )}>↵
    -0.07
    %">↵
    -0.07
    '}>↵
    -0.06
     edt
    -0.06
    "}>↵
    -0.06
    datable
    -0.06
    )."
    -0.06
    POSITIVE LOGITS
     WCHAR
    0.07
     sofas
    0.06
     \/
    0.06
    _hpp
    0.06
     обрат
    0.06
    /angular
    0.06
     TF
    0.06
     cr
    0.06
     Paramount
    0.06
     OF
    0.06
    Act Density 0.002%

    No Known Activations